Knowledge Graph

Graph explorer

Search resolved entities, walk their edges, and read the sentence behind every one.

Entities25 of 207,987

Entity

SVD-Attention

technology1 mentionslast seen Oct 1, 2026

A novel attention mechanism that factorizes low-rank embeddings into principal components for efficient sequence modeling.

Relationships 2

Relationship

SVD-AttentionsupersedesTransformer attention

75% confidence1 supporting mentions

Either name opens that entity’s relationships.

Sources 1

preprintarXivSep 29, 2026SOLAR: SVD-Optimized Lifelong Attention for Recommendation
SVD-Attention factorizes low-rank embeddings into r principal components, computes candidate-to-interest scores in compact space, and applies softmax over those scores. Its bilinear reduction is exact on the rank-r reconstruction, while the normalized output approximates token-level softmax with an explicitly bounded residual. The resulting computation reduces the cost from O(N^2d) to O(Ndr)